A cellular neural network for deformable object modelling

Abstract

This paper presents a new methodology for the deformation of soft objects by drawing an analogy between cellular neural network (CNN) and elastic deformation. An improved CNN model is developed to simulate the deformation of soft objects. A finite volume based method is presented to derive the discrete differential operators over irregular nets for obtaining the internal elastic forces. The proposed methodology not only models the deformation dynamics in continuum mechanics, but it also simplifies the complex deformation problem with simple setting CNN templates. Copyright © 2006 International Federation for Information Processing.